© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30769
    Prev
    Next
    INDEX
    Explanations

    hidden meaning or patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTOR
    -0.08
    å¯Ľ
    -0.07
    antemente
    -0.07
    WithData
    -0.07
    zor
    -0.07
    puter
    -0.07
    ëĥIJ
    -0.07
    нÑĤÑĥ
    -0.07
    ondon
    -0.07
    FetchRequest
    -0.07
    POSITIVE LOGITS
     hidden
    0.23
    éļIJèĹıçļĦ
    0.21
    hidden
    0.20
    éļIJèĹı
    0.20
    éļIJèĹıåľ¨
    0.18
     Hidden
    0.18
    éļIJèĹıçĿĢ
    0.17
    Hidden
    0.17
    -hidden
    0.16
     ÑģкÑĢÑĭ
    0.16
    Activations Density 0.176%

    No Known Activations